Command Code provider plugin for DeepSeek Harness (dsh). Adds Command Code model access, live model catalog, plan-aware model selection, reasoning effort, image input, web search, and multi-account support.
Repo Mars-Sea/dsh-commandcode-provider, read from GitHub 1 min ago. Mars-Sea has not joined Take My Repo.
Mars-Sea/dsh-commandcode-provider is a public repo on GitHub by Mars-Sea. Command Code provider plugin for DeepSeek Harness (dsh). Adds Command Code model access, live model catalog, plan-aware model selection, reasoning effort, image input, web search, and multi-account support. It declares the MIT license on GitHub. It is written mainly in TypeScript, has 490 stars and last changed on 2026-11-22. Nobody has reviewed it on Take My Repo yet, which says nothing about its quality. Read from GitHub on 2026-11-22.
In the maintainer's words. Shown from GitHub; Take My Repo does not keep a copy.
English | 简体中文
Unofficial DeepSeek Harness LLM provider plugin for Command Code, ported from pi-commandcode-provider (MIT).
Community integration. You need your own Command Code account, API key or subscription, and Command Code's terms apply. Not affiliated with Command Code, Inc.
| Verified engines | dsh 0.2.2-rc.1 through 0.2.2-rc.5, and 0.2.3-alpha.2 |
| Node.js | >=24.9 — raised from 22 in 0.16.0, see Node.js 24.9 or newer |
| Install — web | dsh plugin --profile web add @mars-sea/dsh-commandcode-provider@latest |
| Install — terminal | dsh plugin --profile dsh-tui add @mars-sea/dsh-commandcode-provider@latest |
| Config file | $DSH_HOME/settings.yaml → llm-commandcode: |
| API key env | COMMANDCODE_API_KEY |
| Usage dashboard | /commandcode |
dsh plugin add installs a commandcode provider route with the live model catalog.FREE badge, peak/off-peak, image support and context window in the picker; free models first.≈) beside the composer token counter, priced per request from durable session history.web_search tool is served by Command Code (/alpha/web-search) with the same key and endpoint as chat.x-cmd-zdr: 1), off by default.max_tokens./settings → Command Code page.Model picker — plan tier, deal/FREE, peak/off-peak, Image and context annotations:
Usage dashboard — /commandcode per-account report:
Settings page — accounts with live quota, model visibility, privacy switches, connection options:
dsh plugin --profile web add @mars-sea/dsh-commandcode-provider@latest
Version 0.19.0 admits DSH >=0.2.2-rc.1 <0.2.3-0 and >=0.2.3-alpha.2 <0.2.4-0. Profiles on previously supported 0.2.1 RC or 0.2.2 alpha versions can keep using plugin 0.18.3. If your engine is 0.2.3-alpha.1, update to 0.2.3-alpha.2 first. The six tested versions are recorded in dsh.compatibility.dshReleases. Engine compatibility and verification
The Node.js floor was raised from 22 to 24.9 in 0.16.0. On Node 22 or 23, upgrade Node before updating this plugin.
The supported DSH release lines require Node.js 24.9 or newer.
nvm install 24 && nvm use 24 (or any Node 24.9+ distribution) resolves it. Node 24 is a current LTS line.
Older dsh releases are no longer supported: the last plugin release for dsh 0.1.7 is 0.11.17, for 0.1.2–0.1.6 it is 0.11.11, and for the 0.5.0-era line 0.9.1 — all installed by exact version, none maintained.
pnpm 11 holds back new releases.
minimumReleaseAgedefaults to 1440 minutes, so a version published less than a day ago is skipped and@latestresolves to the previous release — silently, with a success exit code. To install a release from the last 24 hours, name it exactly:@mars-sea/dsh-commandcode-provider@0.11.15. This applies to every profile, including the terminal UI below.
Prefer the Web plugin page. A profile that installed this plugin from the npm registry is marked updatable by dsh: sidebar Plugins → open this plugin → the Versions section below its rows lists newer releases, and Update replaces the installed one. An available update also shows an Updatable badge on the card and Update to in the detail header. The host checks the target first, then removes the old version and installs the target, rolling back to the previous version if that install fails. With HMR the new version starts immediately; without HMR dsh reports that a restart is required. API keys live in the dsh credential store and settings in the profile's cordis.patch.yml, so neither is lost when the package is replaced.
Only registry installs under their own package name get a Versions section. Bundles installed from link: / a local path, a Git address, or a tarball (for example dsh plugin add /path/to/dsh-commandcode-provider during development), and bundles shipped with the installation, do not show it. Use the CLI below for those, or remove the bundle and reinstall with the registry command above. The section recommends the newest non-prerelease, non-deprecated version whose engines.dsh admits the running dsh; prereleases can be revealed manually.
CLI (fallback) — same tag as the install, then restart the web app. Each profile updates separately, because the terminal UI owns its own plugin list:
dsh plugin --profile web update @mars-sea/dsh-commandcode-provider@latest dsh plugin --profile dsh-tui update @mars-sea/dsh-commandcode-provider@latest
dsh plugin updateis a pnpm passthrough, not the host's plugin-update path;minimumReleaseAgeabove can silently skip a fresh release there too, so name an exact version when needed.
Easiest via the official CLI (Node.js 22+):
npm i -g command-code@latest
cmd login # macOS/Linux; native Windows: cmdc loginOr skip the CLI: click Sign in to Command Code under Settings → Command Code — the browser opens the commandcode.ai authorization page (the same flow cmd login runs) and the key is stored locally once you approve. You can also create a key on the Keys page and paste it, or export COMMANDCODE_API_KEY="user_...".
The sign-in flow needs the Host and your browser on the same machine (loopback callback). With a remote Host, paste the key manually; a literal composition-level
apiKey, if set, still takes precedence over a signed-in credential.
To verify: after restart, enter your API key in Settings → Command Code and save. Settings → Models shows a Command Code card, and the model picker lists the live catalog under commandcode. Send a message with a model your plan includes.
Each dsh profile owns its own plugin list, so the web install does not reach the terminal — add the plugin to the dsh-tui profile as well, pinned to an exact version (within 24 hours of a release a bare name resolves to the previous build, leaving a fresh install with no /settings → Command Code page and no commandcode models):
dsh plugin --profile dsh-tui add @mars-sea/dsh-commandcode-provider@latest
Then pick the provider in the model selector, or name it directly:
/model commandcode/deepseek/deepseek-v4.1-flash
/model lists every registered provider, with the live catalog and its plan/deal/context annotations; the /commandcode dashboard works there too.
Entering the key. The TUI has no web Models page, so the plugin declares its own page — /settings → Command Code — with the API key, API base, out-of-plan filter, active account and command language. The key field is write-only: it shows whether a key is configured and writes what you type to the credential store, never to a settings document. The same page lists the whole catalog as checkboxes grouped by plan tier, free models first; everything starts checked, and the choice is stored as per-model overrides next to the visibleModels list the web page edits. Custom display names (modelNames) are configurable on the Web settings page only for now; the terminal settings page does not expose them yet (the same boundary as contextWindow, issue #86).
Alternatively set the key outside the TUI. The first match wins:
apiKey in the composition config wins over everything and is always used.apiKeyEnv, COMMANDCODE_API_KEY by default). In a profile that mounts the credentials service (Web, desktop, SDK, ACP) that service owns the order: since 0.2.1-alpha.3 a saved credential wins over the launching environment; earlier releases had the environment first..env and $DSH_HOME/.env apply — a key saved on the page never reaches a headless run.~/.commandcode/auth.json, written by the official CLI.export COMMANDCODE_API_KEY="user_..." # launching environment cmd login # writes ~/.commandcode/auth.json
Making Command Code the default. dsh-TUI pins its own agent route, so its agent-default-model setting does not override it. Override the agent-loop row in your profile patch ($DSH_HOME/profiles/dsh-tui/cordis.patch.yml):
- id: agent-loop inject: [tuiStartup] config: agents: - id: main provider: commandcode model: deepseek/deepseek-v4.1-flash reasoningEffort: max cwd: !!js process.cwd()
The plugin registers a /commandcode slash command showing per-account usage:
/commandcode (or /commandcode status)
Its copy follows the shell's locale: explicit lang: 'en' | 'zh' in the llm-commandcode plugin config wins, otherwise LC_ALL/LANG is read, otherwise it falls back to zh. The web settings page is independent — it follows the browser's language preference.
With several Command Code subscriptions, the plugin switches to the next account automatically when one hits its usage limit:
default account.modelAccountRules).Each account row shows its plan, status and 5-hour/weekly meters; expand it for the full report, or run /commandcode. When a refreshed report shows a spent window, that account also leaves automatic selection until the window resets. The equivalent YAML is in Configure.
Provider ID. This plugin registers the commandcode model route. If you also configure Command Code under llm-pi-ai.config.providers in your profile's cordis.patch.yml, give that entry a distinct key such as commandcode-pi. A duplicate commandcode key can prevent pi-ai from registering its providers and disable Add model provider. To recover, rename the pi-ai entry, update any model selections that reference it, and reload the profile or restart DSH. See issue #129.
Settings → Command Code groups the options as Accounts (keys, sign-in, live quota, pinning, dedicated models), Models & context (out-of-plan filter, visible models, context length, output limit), Privacy & security (zero data retention), Integrations & display (web search, sidebar quota card) and Advanced (API base URL, timeouts, transport retries, image offload). The same options live in $DSH_HOME/settings.yaml and apply immediately, without a restart:
llm-commandcode: apiKeyEnv: COMMANDCODE_API_KEY # first (default) account activeAccount: COMMANDCODE_API_KEY_2 # optional: pin the active account accounts: # optional: rotation order after it - label: Go #2 apiKeyEnv: COMMANDCODE_API_KEY_2 modelAccountRules: # optional: route models to accounts (first match wins) - models: # catalog model ids (multi-select) - deepseek/deepseek-v4-pro account: COMMANDCODE_API_KEY_2 visibleModels: # optional: only these models in pickers; unset shows all - deepseek/deepseek-v4-pro apiBase: https://api.commandcode.ai workingDir: /path/to/project # optional modelsCachePath: ~/.commandcode/models-cache.json requestTimeoutMs: 300000 # default 300s (the official CLI's own budget) streamIdleTimeoutMs: 300000 # default 300s # offloadSeenImagesForCache: true # opt in to CLI cache mitigation showSidebarQuota: true # optional: sidebar plans & quota card (default off) zdr: true # optional: zero-data-retention upstreams only (default off) # contextWindow: 131072 # optional: custom context length for every model # contextWindowOverrides: # optional: per-model context lengths; wins over contextWindow # deepseek/deepseek-v4-pro: 65536 # maxOutputTokens: 65536 # optional: per-turn output limit; 0 sends no max_tokens # modelNames: { "deepseek/deepseek-v4.1-flash": "DeepSeek V4.1 Flash" } # optional: display-name overrides by catalog id
| Option | Effect |
|---|---|
contextWindow, contextWindowOverrides |
Replace the catalog context_length the harness meters and compacts on (issue #86). Use it when the catalog over-reports the window (sessions then fail with context_length_exceeded) or under-reports it (sessions compact too early). Whole tokens in 1 – 10,000,000; 32K/1M shorthand accepted. |
maxOutputTokens |
Per-turn max_tokens cap. Every request already carries max_tokens, resolved as the smallest of the model's published ceiling, the runtime-learned ceiling and the gateway cap of 131,072 — a passive hard limit that cuts the answer with no warning to the model. A positive number can only tighten it; 0 sends no field at all, which is the fix for answers cut off mid-sentence (0 affects the CLI and OpenAI transports only; Claude's Anthropic Messages endpoint requires the field). An empty field clears the setting — it is not the same as writing 0. |
offloadSeenImagesForCache |
On the CLI transport a new image can make the reported prompt cache retreat to the first historical image even when every previous request message is byte-identical. Enabling it replaces an older image with a stable text placeholder once this model has answered with it, so later text stays cached without replaying old pixels. It mitigates the cost spike but does not repair Command Code's multimodal cache behavior, and the model cannot inspect an offloaded image again without rereading the source file. Off by default. Live evidence. |
modelNames |
Optional map of catalog model id → custom display name; only the picker label (LlmModelInfo.name) changes, so external tools that match on the model name string (peak-hour reminders, cache-pricing plugins) can be made to line up — our default (CC) suffix and upstream's (latest) suffix are what break them. Unset or empty (the default) keeps the name exactly as today: ${catalogName} (CC), with any upstream (latest) preserved; an unknown model with no catalog row still shows the bare id. The model id, request body, pricing, peak labels, price table, commandcode/prices wire and Remote descriptor count are unchanged; sorting still uses the catalog original name, so renaming never reorders the picker. Configurable on the Web settings page only for now — the terminal settings page is not wired up. |
When your deployment mounts the web capability (@deepseek-ai/dsh-web + @deepseek-ai/dsh-tool-web), the model's web_search tool is served by this plugin's commandcode search provider — it calls the Command Code Provider API's /alpha/web-search endpoint with the same API key and base URL as chat, so no separate search key, endpoint or model is needed.
On by default. The "Serve dsh web search with Command Code" toggle (webSearch) selects commandcode as the active search backend; turning it off hands the selection back to whichever backend was there before (a sibling search plugin such as modsearch keeps working). The change takes effect on the next search — no restart.
commandcode on ctx.web only when the web service is present; without it this stays a chat-only plugin.commandcode registered but unselected and reports that state. It takes over only while nothing else pins the field, remembers the backend it displaced, and restores it when the toggle goes off or the plugin unloads. To pin it durably, set searchProvider: commandcode (or $DSH_WEB_SEARCH_PROVIDER=commandcode).numResults from the dsh tool is clamped to the Command Code range (1–10, default 5); results map to the dsh WebSearchSource shape (url/title/snippet).This reuses the Command Code Provider API directly (like the official CLI's built-in
web_search), so it is distinct from a DeepSeek-native search backend.
Command Code can serve a request only through upstreams that retain no prompts or completions and never train on them — the same opt-in the official CLI exposes as CMD_ZDR=1, and the x-cmd-zdr: 1 header on the Provider API (official docs).
Off by default. Turn it on with the "Zero data retention (ZDR)" toggle (zdr) in the Privacy & security card, or in your profile config.
422 cmd_zdr_no_providers; the request is never retried without the header.stop sequences — requests carrying one fail./provider/v1/chat/completions passes it back as reasoning_content, /alpha/generate carries it as a reasoning block inside the rebuilt assistant turn. Only tool calls with a paired tool result are replayed.inputSchema, a generated root $ref) no longer fails the turn with schema must be a JSON Schema of 'type: "object"'.The plugin only communicates between your local dsh profile and your Command Code account: locally it touches only the credential store and the models cache (plus ~/.commandcode/auth.json as a last-resort fallback); on the network it calls only the Command Code API. No telemetry. With zero data retention on, chat requests require a ZDR upstream; models without one fail instead of running without the protection.
cordis.patch.yml and comment out (or remove) the llm-commandcode row, or set disabled: true, then restart.dsh plugin --profile web remove @mars-sea/dsh-commandcode-provider. Your API key in the dsh credential store and ~/.commandcode/auth.json are left untouched.npm install npm run typecheck # tsc --noEmit npm run build # tsdown -> lib/
To try a local build in a profile: dsh plugin --profile web add /path/to/dsh-commandcode-provider. After changing src/, re-run npm run build and restart the app.
The package exports the plugin root, /client, /locale/*.json, and /package.json. Source remains in the repository; the unpackaged ./src/* export was removed. npm run test:pack checks declared entry points against the actual packed file list.
The engineering detail behind this README lives under docs/agent-reference/:
engines.dsh admissionGitHub Repository · GitHub Releases · npm Package · Linux.do 社区
MIT — see LICENSE. Portions ported from pi-commandcode-provider (MIT).
Mars-Sea/dsh-commandcode-provider is a public repo on GitHub by Mars-Sea. Command Code provider plugin for DeepSeek Harness (dsh). Adds Command Code model access, live model catalog, plan-aware model selection, reasoning effort, image input, web search, and multi-account support.
It declares the MIT license on GitHub.
Its maker tagged it for Windows and Linux. That is declared by the maker; Take My Repo has not tested it.
Open "Take it" on its page: Take My Repo writes an install plan for your machine and hands it to your AI agent (Claude Code, Codex or Cursor), which asks you before each step. Take My Repo has not tested it on any machine.
Its last change on GitHub was on 2026-11-22. GitHub counts 7 open issues and pull requests. Take My Repo does not judge from that whether it is maintained.
Nobody has reviewed it on Take My Repo yet, which says nothing about its quality.
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode,DeepSeek Harness and more. Only official website: ccswitch.io


The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Terminal multiplexer for AI coding agents. Run Claude Code, Codex, OpenCode, Gemini CLI and more side by side in one tmux TUI, with live status, worktrees and diff review. Discord: discord.gg/ecS88An7pF
Native iPhone companion plugin for DeepSeek Harness — sessions, approvals, questions, notifications, and secure remote access.
一个基于MTranServer 的 Pot-app 翻译插件。
一个基于BergaRust 的 Pot-app 翻译插件。
📄 Document generation microservice based on Spring Boot + poi-tl. RESTful API for Word/Excel template rendering. Docker & Go SDK supported.
Coarena plugin for Magpie and OpenCode: models, API key authentication, and daily usage.
This page is also available as structured data, with the same sources and dates.
/api/v1/resources/gh/Mars-Sea/dsh-commandcode-providerTake My Repo has not tested this on your machine. Requirements come from the project's own documentation.
